A First Look at Deep Learning Apps on Smartphones
This work provides insights for app developers, smartphone vendors, and deep learning researchers by revealing real-world practices and challenges in mobile deep learning deployment.
The study conducted the first empirical analysis of 16,500 popular Android apps to understand how deep learning is used in smartphone applications, identifying early adopters, use cases, and model characteristics, and highlighting both the growth of mobile deep learning frameworks and the need for optimizations and protections.
We are in the dawn of deep learning explosion for smartphones. To bridge the gap between research and practice, we present the first empirical study on 16,500 the most popular Android apps, demystifying how smartphone apps exploit deep learning in the wild. To this end, we build a new static tool that dissects apps and analyzes their deep learning functions. Our study answers threefold questions: what are the early adopter apps of deep learning, what do they use deep learning for, and how do their deep learning models look like. Our study has strong implications for app developers, smartphone vendors, and deep learning R\&D. On one hand, our findings paint a promising picture of deep learning for smartphones, showing the prosperity of mobile deep learning frameworks as well as the prosperity of apps building their cores atop deep learning. On the other hand, our findings urge optimizations on deep learning models deployed on smartphones, the protection of these models, and validation of research ideas on these models.